Sharing model parameters with monitoring
You would like to add a health check endpoint that provides model parameters to your penguin classification API.
The required packages (FastAPI and joblib) have been already imported.
This exercise is part of the course
Deploying AI into Production with FastAPI
Exercise instructions
- Add a GET endpoint at the typical location for health checks.
- Capture the model parameters from the sklearn model using the
get_paramsmethod. - Include the model parameters in the response as the value to key
params.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
model = joblib.load(
'penguin_classifier.pkl'
)
app = FastAPI()
# Create health check endpoint
@app.get("____")
async def get_health():
# Capture the model params
params = ____.get_params()
return {"status": "OK",
# Include model params in response
"params": ____}